4 Services from diomedes.tail1c6d58.ts.net

Runs LLM inference on a private GPU fleet (Qwen3 8B–27B, VL 30B) with per-call USDC micropayment via the x402 protocol, settling on Base in seconds.

Runs vision-language model inference (Qwen VL 30B) on a private GPU fleet, billed per-call in USDC via the x402 payment protocol

Runs a deep LLM inference call on a private GPU fleet (Qwen3-27B-class) with verifier-gated correctness guarantees, paid per-call in USDC via x402.

Returns metadata (row count, name) for a named dataset hosted on the Argo Hub private GPU/data platform, paid via x402 USDC micropayment.